SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.11735 · ICML · 2024

Learning with 3D rotations, a hitchhiker's guide to SO(3)

Georg Martius, Anna Levina, A Geist, Jonas Frey, Mikel Zhobro

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 9 functions out of this paper's own repositories and ran 7 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
martius-lab/hitchhiking-rotations canonical 7 of 9
FunctionStatusWhere it lives
batch_normalize Ran martius-lab/hitchhiking-rotations/hitchhiking_rotations/datasets/fourier_dataset.py
code served (permissive licence) · get_code("706162faeafa4022")
euler_angles_to_matrix Ran martius-lab/hitchhiking-rotations/hitchhiking_rotations/utils/euler_helper.py
code served (permissive licence) · get_code("179c7ef844778bd0")
get_cfg_cube_image_to_pose Ran martius-lab/hitchhiking-rotations/hitchhiking_rotations/cfgs/cfg_cube_image_to_pose.py
code served (permissive licence) · get_code("d718ad27ed5d1046")
get_cfg_pcd_to_pose Ran martius-lab/hitchhiking-rotations/hitchhiking_rotations/cfgs/cfg_pcd_to_pose.py
code served (permissive licence) · get_code("294058c30c63af89")
get_cfg_pose_to_cube_image Ran martius-lab/hitchhiking-rotations/hitchhiking_rotations/cfgs/cfg_pose_to_cube_image.py
code served (permissive licence) · get_code("381abec716842344")
get_cfg_pose_to_fourier Ran martius-lab/hitchhiking-rotations/hitchhiking_rotations/cfgs/cfg_pose_to_fourier.py
code served (permissive licence) · get_code("c346a52198ed152c")
matrix_to_euler_angles Ran martius-lab/hitchhiking-rotations/hitchhiking_rotations/utils/euler_helper.py
code served (permissive licence) · get_code("668ea5945b1b3c1c")
input_to_fourier Not yet run martius-lab/hitchhiking-rotations/hitchhiking_rotations/datasets/fourier_dataset.py
code served (permissive licence) · get_code("8af2f3b8b52ec490")
random_fourier_function Not yet run martius-lab/hitchhiking-rotations/hitchhiking_rotations/datasets/fourier_dataset.py
code served (permissive licence) · get_code("7d24b4d6befbb747")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Many settings in machine learning require the selection of a rotation representation. However, choosing a suitable representation from the many available options is challenging. This paper acts as a survey and guide through rotation representations. We walk through their properties that harm or benefit deep learning with gradient-based optimization. By consolidating insights from rotation-based learning, we provide a comprehensive overview of learning functions with rotation representations. We provide guidance on selecting representations based on whether rotations are in the model's input or output and whether the data primarily comprises small angles. The project code is available at: github.com/martius-lab/hitchhiking-rotations In machine learning, we want to choose the representation

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2404.11735")
get_code_for_paper("2404.11735")
have("2404.11735")

Connect an agent — have() is free.